Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Follow-up Questioning Consistency research benchmarks · SOTA2 Research

Follow-up Questioning Consistency

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

MultiArith (unseen)

UNWAVERING-FQ (+ SFT + DPO)

18.33Average Success Count

12

Feb 26, 2026

StrategyQA (unseen)

Vicuna-7B + SFT

42.65Average Success Count (M.)

12

Feb 26, 2026

CoinFlip (unseen)

UNWAVERING-FQ (Vicuna-7B + SFT + DPO)

52.2Baseline Consistency Score

3

Feb 26, 2026

Popular datasets

StrategyQA MultiArith Coinflip

Follow for updates

Join SOTA2 Contact